Skip to content

Benchmark

SWT-Bench

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

69.3%
Mean
69.3%
Median
0%
Std dev
69.3%
10th percentile
69.3%
90th percentile
69.3%
Min

Leaderboard

#ModelScore
1MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.3%

Data credits: Data by LLM Stats